Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00030
Ming Meng, Shaojun Liu
In this paper, we propose a panorama stitching algorithm based on asymmetric bidirectional optical flow. This algorithm expects multiple photos captured by fisheye lens cameras as input, and then, through the proposed algorithm, these photos can be merged into a high-quality 360-degree spherical panoramic image. For photos taken from a distant perspective, the parallax among them is relatively small, and the obtained panoramic image can be nearly seamless and undistorted. For photos taken from a close perspective or with a relatively large parallax, a seamless though partially distorted panoramic image can also be obtained. Besides, with the help of Graphics Processing Unit (GPU), this algorithm can complete the whole stitching process at a very fast speed: typically, it only takes less than 30s to obtain a panoramic image of 9000-by-4000 pixels, which means our panorama stitching algorithm is of high value in many real-time applications. Our code is available at https://github.com/MungoMeng/Panorama-OpticalFlow.
{"title":"High-quality Panorama Stitching based on Asymmetric Bidirectional Optical Flow","authors":"Ming Meng, Shaojun Liu","doi":"10.1109/ICCIA49625.2020.00030","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00030","url":null,"abstract":"In this paper, we propose a panorama stitching algorithm based on asymmetric bidirectional optical flow. This algorithm expects multiple photos captured by fisheye lens cameras as input, and then, through the proposed algorithm, these photos can be merged into a high-quality 360-degree spherical panoramic image. For photos taken from a distant perspective, the parallax among them is relatively small, and the obtained panoramic image can be nearly seamless and undistorted. For photos taken from a close perspective or with a relatively large parallax, a seamless though partially distorted panoramic image can also be obtained. Besides, with the help of Graphics Processing Unit (GPU), this algorithm can complete the whole stitching process at a very fast speed: typically, it only takes less than 30s to obtain a panoramic image of 9000-by-4000 pixels, which means our panorama stitching algorithm is of high value in many real-time applications. Our code is available at https://github.com/MungoMeng/Panorama-OpticalFlow.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124747975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00048
Min-Ho Kim, Kyeong-Bin Park, Ki-Seok Chung
The extended min-sum algorithm (EMS) for decoding non-binary low density parity check (NB-LDPC) codes reduces the decoding complexity by truncating the message vector by retaining only the most reliable symbols. However, the EMS algorithm does not consider that the noise of the received codeword is gradually reduced as the iteration count goes up. In this paper, we propose a low-complexity adaptive EMS algorithm, called threshold-based EMS (TB-EMS). The TB-EMS algorithm has a simple adaptive rule to calculate the new message vector length compared to the A-EMS. The proposed algorithm selects one of two message vector lengths. Experimental results show that the proposed algorithm reduces the decoding complexity with minimal performance degradation compared with the EMS algorithm. Further, the decoding performance of the TB-EMS is better than A-EMS.
{"title":"A Low-Complexity Adaptive Extended Min-Sum Algorithm for Non-Binary LDPC Codes","authors":"Min-Ho Kim, Kyeong-Bin Park, Ki-Seok Chung","doi":"10.1109/ICCIA49625.2020.00048","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00048","url":null,"abstract":"The extended min-sum algorithm (EMS) for decoding non-binary low density parity check (NB-LDPC) codes reduces the decoding complexity by truncating the message vector by retaining only the most reliable symbols. However, the EMS algorithm does not consider that the noise of the received codeword is gradually reduced as the iteration count goes up. In this paper, we propose a low-complexity adaptive EMS algorithm, called threshold-based EMS (TB-EMS). The TB-EMS algorithm has a simple adaptive rule to calculate the new message vector length compared to the A-EMS. The proposed algorithm selects one of two message vector lengths. Experimental results show that the proposed algorithm reduces the decoding complexity with minimal performance degradation compared with the EMS algorithm. Further, the decoding performance of the TB-EMS is better than A-EMS.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127651761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00045
Chen Ying, Fan Songhai, Wang Qiaomei, Wu Tianbao, Luo Lei, Mai Xiaomin, Gong Yiyu
Aiming at the problem that traditional traveling wave protection is difficult to take into account both quick-action and selectivity, an intelligent fault identification method for HVDC transmission lines based on S-transform multi-scale area is proposed. This method combines Radial Basis Function Network (RBFN) can accurately distinguish between internal and external faults, and at the same time achieve fault pole selection. First, the discrete S-transform is performed on the transient current signal, and multiple frequency scale signals are selected to calculate the area of the frequency signal after the fault. The S-transform multi-scale area is used to characterize the internal and external fault features and fault pole characteristics. The S-transform multi-scale area is used to form a feature vector, and the feature vector set is divided into a training set and a test set. The training set is trained to obtain an RBFN model, and the test set is used for testing. The prediction result obtained is the classification of different fault types. A large number of simulation results show that the method can effectively realize the internal and external fault identification and fault pole selection under different fault distances and different transition resistances, and has a strong ability to withstand transition resistances.
{"title":"A novel fault identification method for HVDC transmission line based on Stransform multi-scale area","authors":"Chen Ying, Fan Songhai, Wang Qiaomei, Wu Tianbao, Luo Lei, Mai Xiaomin, Gong Yiyu","doi":"10.1109/ICCIA49625.2020.00045","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00045","url":null,"abstract":"Aiming at the problem that traditional traveling wave protection is difficult to take into account both quick-action and selectivity, an intelligent fault identification method for HVDC transmission lines based on S-transform multi-scale area is proposed. This method combines Radial Basis Function Network (RBFN) can accurately distinguish between internal and external faults, and at the same time achieve fault pole selection. First, the discrete S-transform is performed on the transient current signal, and multiple frequency scale signals are selected to calculate the area of the frequency signal after the fault. The S-transform multi-scale area is used to characterize the internal and external fault features and fault pole characteristics. The S-transform multi-scale area is used to form a feature vector, and the feature vector set is divided into a training set and a test set. The training set is trained to obtain an RBFN model, and the test set is used for testing. The prediction result obtained is the classification of different fault types. A large number of simulation results show that the method can effectively realize the internal and external fault identification and fault pole selection under different fault distances and different transition resistances, and has a strong ability to withstand transition resistances.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"517 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123098456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00041
H. Deng, Tao Yang
Negative selection algorithm (NSA) is an important detectors training algorithm in artificial immune system (AIS). In NSAs, the self radius and location of detectors affect the performance of algorithms. However, the traditional NSAs preset the self radius empirically and generate detectors randomly without considering the distribution of antigens resulting in the performance of AIS varies greatly in different applications. To deal with these limitations, an adaptive immunoregulation based real value negative selection algorithm (AINSA) is proposed in this paper. AINSA utilizes the "adaptive immunoregulation" mechanism to calculate the self radius and optimize the location of the candidate detectors. In this way, AINSA can attain the suitable self radius for different application and effectively generate the detectors in the region where antigens distribute densely. The experimental results show, on the artificial dataset and the UCI standard datasets, AINSA can reach the higher detection rate with better detectors generation efficiency compared to the classical RNSA and V-detector algorithm.
{"title":"A negative selection algorithm based on adaptive immunoregulation","authors":"H. Deng, Tao Yang","doi":"10.1109/ICCIA49625.2020.00041","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00041","url":null,"abstract":"Negative selection algorithm (NSA) is an important detectors training algorithm in artificial immune system (AIS). In NSAs, the self radius and location of detectors affect the performance of algorithms. However, the traditional NSAs preset the self radius empirically and generate detectors randomly without considering the distribution of antigens resulting in the performance of AIS varies greatly in different applications. To deal with these limitations, an adaptive immunoregulation based real value negative selection algorithm (AINSA) is proposed in this paper. AINSA utilizes the \"adaptive immunoregulation\" mechanism to calculate the self radius and optimize the location of the candidate detectors. In this way, AINSA can attain the suitable self radius for different application and effectively generate the detectors in the region where antigens distribute densely. The experimental results show, on the artificial dataset and the UCI standard datasets, AINSA can reach the higher detection rate with better detectors generation efficiency compared to the classical RNSA and V-detector algorithm.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115264916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00038
B. Zhu, Weiqiang Tang, Xiai Mao, Wenchuan Yang
Consumer purchase prediction is of great significance for reducing marketing costs and improving return on investment of companies. Recently, spatial-temporal data mining has aroused increasing concern. In this paper, we propose a hybrid deep learning model (EE-CNN) for purchase prediction, which combines entity embedding and convolutional neural networks. In empirical experiments, we first explore the purchase location pattern of different consumer groups on data sets from a retail company of China. After that, our proposed EE-CNN model is utilized to predict consumer purchase behavior. It turns out that location data can help improve the performance of purchase prediction models in general. Meanwhile, our proposed EE-CNN model outperforms baselines used in the experiments. Our research provides significant guidelines for the marketing decisions of enterprise marketers.
{"title":"Location-based Hybrid Deep Learning Model for Purchase Prediction","authors":"B. Zhu, Weiqiang Tang, Xiai Mao, Wenchuan Yang","doi":"10.1109/ICCIA49625.2020.00038","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00038","url":null,"abstract":"Consumer purchase prediction is of great significance for reducing marketing costs and improving return on investment of companies. Recently, spatial-temporal data mining has aroused increasing concern. In this paper, we propose a hybrid deep learning model (EE-CNN) for purchase prediction, which combines entity embedding and convolutional neural networks. In empirical experiments, we first explore the purchase location pattern of different consumer groups on data sets from a retail company of China. After that, our proposed EE-CNN model is utilized to predict consumer purchase behavior. It turns out that location data can help improve the performance of purchase prediction models in general. Meanwhile, our proposed EE-CNN model outperforms baselines used in the experiments. Our research provides significant guidelines for the marketing decisions of enterprise marketers.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132616971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00044
Kai Li, Yidan Yedda Xing, Haijia Zhu, Wei Nai
Electricity consumption reflects the development level of a certain region to a great extent, and it is always in a changing process with fluctuation. Entities or agencies who provide the electricity power supply services are always eager to know the data of regional electricity consumption, and hope to obtain the accurate forecast of future power consumption from these data, so that more appropriate and reasonable power supply service arrangement can be implemented. Till now, many scholars have reported their research on doing forecasting work by employing algorithms for regression such as Grey Theory or Random Forest, however, there are some drawbacks in both algorithms in using available data for prediction. In this paper, a short-term hybrid forecasting approach has been proposed based on both algorithms, it can not only realize the prediction from relatively less available data, but ensure high accuracy in prediction as well. By an empirical study on the electricity power consumption of a certain region in central western China, the effectiveness of the proposed method is verified.
{"title":"A Short-Term Hybrid Forecasting Approach for Regional Electricity Consumption Based on Grey Theory and Random Forest","authors":"Kai Li, Yidan Yedda Xing, Haijia Zhu, Wei Nai","doi":"10.1109/ICCIA49625.2020.00044","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00044","url":null,"abstract":"Electricity consumption reflects the development level of a certain region to a great extent, and it is always in a changing process with fluctuation. Entities or agencies who provide the electricity power supply services are always eager to know the data of regional electricity consumption, and hope to obtain the accurate forecast of future power consumption from these data, so that more appropriate and reasonable power supply service arrangement can be implemented. Till now, many scholars have reported their research on doing forecasting work by employing algorithms for regression such as Grey Theory or Random Forest, however, there are some drawbacks in both algorithms in using available data for prediction. In this paper, a short-term hybrid forecasting approach has been proposed based on both algorithms, it can not only realize the prediction from relatively less available data, but ensure high accuracy in prediction as well. By an empirical study on the electricity power consumption of a certain region in central western China, the effectiveness of the proposed method is verified.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114831281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00023
Caixin Zhu, Huaiyao Zhang, Yun Tang
People have relatively higher requirements for image storage in some specific fields, such as high-resolution cultural relic data image, medical image, infrared remote sensing image, high-precision astronomical observation image. There cannot be any pixel loss in the storage process, so the image can only be compressed by lossless compression. In this paper, a lossless image compression algorithm based on the neural network of long short-term memory (LSTM) is proposed: a LSTM model predictor based on attention mechanism is built by utilizing the memory characteristic of cyclic neural network. The previous pixel value of the image was taken as the input of the model, then the predicted pixel was obtained through the cyclic neural network, and finally the calculated difference between these values was encoded by the mixed run-length encoding and Golomb-Rice encoding. Compared with the traditional predictive lossless image compression algorithm, this algorithm proposed here comprehensively considers the correlation between more pixels and encoded pixels. The experimental results show that compared with the lossless image compression algorithms JPEG-LS and CALIC, the proposed algorithm improves the compression rate by 25% and 12% respectively.
{"title":"Lossless Image Compression Algorithm Based on Long Short-term Memory Neural Network","authors":"Caixin Zhu, Huaiyao Zhang, Yun Tang","doi":"10.1109/ICCIA49625.2020.00023","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00023","url":null,"abstract":"People have relatively higher requirements for image storage in some specific fields, such as high-resolution cultural relic data image, medical image, infrared remote sensing image, high-precision astronomical observation image. There cannot be any pixel loss in the storage process, so the image can only be compressed by lossless compression. In this paper, a lossless image compression algorithm based on the neural network of long short-term memory (LSTM) is proposed: a LSTM model predictor based on attention mechanism is built by utilizing the memory characteristic of cyclic neural network. The previous pixel value of the image was taken as the input of the model, then the predicted pixel was obtained through the cyclic neural network, and finally the calculated difference between these values was encoded by the mixed run-length encoding and Golomb-Rice encoding. Compared with the traditional predictive lossless image compression algorithm, this algorithm proposed here comprehensively considers the correlation between more pixels and encoded pixels. The experimental results show that compared with the lossless image compression algorithms JPEG-LS and CALIC, the proposed algorithm improves the compression rate by 25% and 12% respectively.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124478400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00016
Hua-Hui Xu, Ruoli Tang
A novel particle swarm optimization with elite opposition-based learning algorithm is proposed in an attempt to improve the performance on solving large-scale optimization problems (LSOP) in maximum power point tracking (MPPT) of photovoltaic system. The standard particle swarm optimization (PSO) algorithm shows its weakness on LSOP, such as easily falling into local optimum, slow convergence and low accuracy at later evolution process. Therefore, this paper develops a modified PSO algorithm based on elite opposition-based learning mechanism and adaptive multi-context cooperatively coevolving (AM-CC) framework. In every iteration, the current high-priority individuals execute dynamic generalized opposition-based learning to generate their opposite solutions which enhance the ability of local exploration and help the particles escape from local optimum. The simulation experiments are conducted on a comprehensive set of benchmarks (up to 2000 real-valued variables), as well as on a large-scale MPPT application. Compared with some state-of-the-art variants of PSO and differential evolution (DE), the results show that the improved algorithm has higher convergence speed and accuracy. Besides, it can avoid premature phenomenon effectively and is suitable to solve the large-scale optimization problem.
{"title":"Particle swarm optimization with adaptive elite opposition-based learning for large-scale problems","authors":"Hua-Hui Xu, Ruoli Tang","doi":"10.1109/ICCIA49625.2020.00016","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00016","url":null,"abstract":"A novel particle swarm optimization with elite opposition-based learning algorithm is proposed in an attempt to improve the performance on solving large-scale optimization problems (LSOP) in maximum power point tracking (MPPT) of photovoltaic system. The standard particle swarm optimization (PSO) algorithm shows its weakness on LSOP, such as easily falling into local optimum, slow convergence and low accuracy at later evolution process. Therefore, this paper develops a modified PSO algorithm based on elite opposition-based learning mechanism and adaptive multi-context cooperatively coevolving (AM-CC) framework. In every iteration, the current high-priority individuals execute dynamic generalized opposition-based learning to generate their opposite solutions which enhance the ability of local exploration and help the particles escape from local optimum. The simulation experiments are conducted on a comprehensive set of benchmarks (up to 2000 real-valued variables), as well as on a large-scale MPPT application. Compared with some state-of-the-art variants of PSO and differential evolution (DE), the results show that the improved algorithm has higher convergence speed and accuracy. Besides, it can avoid premature phenomenon effectively and is suitable to solve the large-scale optimization problem.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130570101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-06-01DOI: 10.1109/ICCIA49625.2020.00036
Faqiang Sun, Li Zhao, Bo Zhou, Yong Wang
Network operators often need a clear visibility of the mobile APPs and their user scales running in the network traffic. This is critical for network management and network security. Analysis of the network traffic using the extracted APP features and user fingerprints is helpful for effective network operations, management, and security monitoring of LANs, MANs, and WANs. In China, the number of mobile APP users continues to increase, and the proportion of Internet users using mobile APPs to access the Internet far exceeds that of computers, making this task significant and difficult. The traditional methods are mainly APP identifications or identifications of specific APP users, which cannot satisfy the requirements of globally monitoring of APPs and their user scales at the same time. Especially when many users share the same network IPs (4G, home broadband, NAT), this work becomes challenging and time-consuming. This paper proposes an automatic fingerprint extraction approach of mobile APP users in network traffic. By analyzing the plaintext of the HTTP requests initiated by APPs in training datasets, we extract the APPs’ features and the users’ fingerprints simultaneously. Both of them are the combinations of strings which are distinguishable of APPs and their users in the network traffic. The proposed method is evaluated with the top 49 popular APPs in Huawei App Store. The experimental results show that the recalls of the extractions of APPs’ features and users’ fingerprints are respectively 77.5% and 55.1% in total.
{"title":"Automatic Fingerprint Extraction of Mobile APP Users in Network Traffic","authors":"Faqiang Sun, Li Zhao, Bo Zhou, Yong Wang","doi":"10.1109/ICCIA49625.2020.00036","DOIUrl":"https://doi.org/10.1109/ICCIA49625.2020.00036","url":null,"abstract":"Network operators often need a clear visibility of the mobile APPs and their user scales running in the network traffic. This is critical for network management and network security. Analysis of the network traffic using the extracted APP features and user fingerprints is helpful for effective network operations, management, and security monitoring of LANs, MANs, and WANs. In China, the number of mobile APP users continues to increase, and the proportion of Internet users using mobile APPs to access the Internet far exceeds that of computers, making this task significant and difficult. The traditional methods are mainly APP identifications or identifications of specific APP users, which cannot satisfy the requirements of globally monitoring of APPs and their user scales at the same time. Especially when many users share the same network IPs (4G, home broadband, NAT), this work becomes challenging and time-consuming. This paper proposes an automatic fingerprint extraction approach of mobile APP users in network traffic. By analyzing the plaintext of the HTTP requests initiated by APPs in training datasets, we extract the APPs’ features and the users’ fingerprints simultaneously. Both of them are the combinations of strings which are distinguishable of APPs and their users in the network traffic. The proposed method is evaluated with the top 49 popular APPs in Huawei App Store. The experimental results show that the recalls of the extractions of APPs’ features and users’ fingerprints are respectively 77.5% and 55.1% in total.","PeriodicalId":237536,"journal":{"name":"2020 5th International Conference on Computational Intelligence and Applications (ICCIA)","volume":"78 15","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120821103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：